Auto-generate optimal task schedules. Schedules tasks with estimated_duration based on priority, deadlines, and dependencies. By default schedules on weekdays only and skips tasks that already have a planned_start (use force_override to override). Args: algorithm: Algorithm name. One of: greedy (...
AI agents use optimize_schedule to create or update resources in Taskdog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Taskdog environment.
This tool creates or modifies scheduling metadata (planned_start times, task ordering) on tasks. While reversible through subsequent reschedules or manual updates, it substantially alters task state. It does not execute tasks, delete them, or move money, so it fits Write rather than Execute or Destructive.
From the tool's definition The tool 'auto-generate optimal task schedules' and 'Schedules tasks with estimated_duration' indicates it modifies task planned_start times and scheduling state. The force_override parameter confirms it writes scheduling decisions that persist.
Documented attack patterns abuse exactly the kind of access optimize_schedule gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Taskdog, and nothing reaches the server without passing your rules. This is the rule we recommend for optimize_schedule:
{
"version": "1",
"default": "deny",
"tools": {
"optimize_schedule": {
"limits": [
{
"counter": "optimize_schedule_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}optimize_schedule stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Auto-generate optimal task schedules. Schedules tasks with estimated_duration based on priority, deadlines, and dependencies. By default schedules on weekdays only and skips tasks that already have a planned_start (use force_override to override). Args: algorithm: Algorithm name. One of: greedy (front-load), balanced (even distribution), backward (JIT from deadline), priority_first (priority only), earliest_deadline (EDF), round_robin (parallel progress), dependency_aware (CPM), genetic (evolutionary), monte_carlo (random sampling). Use list_algorithms() to discover available algorithms. max_hours_per_day: Maximum work hours per day (e.g., 6.0 or 8.0) start_date: Optimization start date in ISO format (e.g., '2025-12-15' or '2025-12-15T09:00:00'). Defaults to server current time when omitted. task_ids: Specific task IDs to optimize. If omitted, all schedulable tasks are considered. force_override: If True, override existing schedules include_all_days: If True, schedule on weekends and holidays too Returns: Optimization result with successful_tasks, failed_tasks, daily_allocations, and summary metrics. It is categorised as a Write tool in the Taskdog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Taskdog MCP server in PolicyLayer and add a rule for optimize_schedule: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Taskdog. Nothing to install.
optimize_schedule is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the optimize_schedule rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for optimize_schedule. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
optimize_schedule is provided by the Taskdog MCP server (kohei-wada/taskdog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Taskdog, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 Taskdog tools catalogued and risk-classified — across an index of 43,000+ MCP servers.